Deep reinforcement hashing with redundancy elimination for effective image retrieval

作者：

Highlights：

• Block-wise Hash Code Inference is utilized to preserve arbitrarily large global similarity relationship.

• Hash Code Mapping based on Multi-binary Classification is established to be trained in a point-wise style.

• Hash Bits De-redundancy based on Deep Reinforcement Learning is created to eliminate redundant or even harmful bits from hash codes while preserving the retrieval accuracy.

摘要

•Block-wise Hash Code Inference is utilized to preserve arbitrarily large global similarity relationship.•Hash Code Mapping based on Multi-binary Classification is established to be trained in a point-wise style.•Hash Bits De-redundancy based on Deep Reinforcement Learning is created to eliminate redundant or even harmful bits from hash codes while preserving the retrieval accuracy.

论文关键词：Deep reinforcement hashing,Redundancy elimination,Image retrieval,Block-wise hash code inference,Hash code mapping,Hash code de-redundancy

论文评审过程：Received 13 April 2019, Revised 7 September 2019, Accepted 15 November 2019, Available online 20 November 2019, Version of Record 4 December 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.107116